1 / 76

Scalable Many-Core Memory Systems Topic 2 : Emerging Technologies and Hybrid Memories

Scalable Many-Core Memory Systems Topic 2 : Emerging Technologies and Hybrid Memories. Prof. Onur Mutlu http://www.ece.cmu.edu/~omutlu onur@cmu.edu HiPEAC ACACES Summer School 2013 July 15-19, 2013. Requirements from an Ideal Memory System. Traditional Enough capacity Low cost

lucio
Télécharger la présentation

Scalable Many-Core Memory Systems Topic 2 : Emerging Technologies and Hybrid Memories

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript

  1. Scalable Many-Core Memory Systems Topic 2: Emerging Technologies and Hybrid Memories Prof. Onur Mutlu http://www.ece.cmu.edu/~omutlu onur@cmu.edu HiPEAC ACACES Summer School 2013 July 15-19, 2013

  2. Requirements from an Ideal Memory System • Traditional • Enough capacity • Low cost • High system performance (high bandwidth, low latency) • New • Technology scalability: lower cost, higher capacity, lower energy • Energy (and power) efficiency • QoS support and configurability (for consolidation)

  3. Requirements from an Ideal Memory System • Traditional • Higher capacity • Continuous low cost • High system performance (higher bandwidth, low latency) • New • Technology scalability: lower cost, higher capacity, lower energy • Energy (and power) efficiency • QoS support and configurability (for consolidation) Emerging, resistive memory technologies (NVM) can help

  4. Agenda • Major Trends Affecting Main Memory • Requirements from an Ideal Main Memory System • Opportunity: Emerging Memory Technologies • Conclusions • Discussion

  5. The Promise of Emerging Technologies • Likely need to replace/augment DRAM with a technology that is • Technology scalable • And at least similarly efficient, high performance, and fault-tolerant • or can be architected to be so • Some emerging resistive memory technologies appear promising • Phase Change Memory (PCM)? • Spin Torque Transfer Magnetic Memory (STT-MRAM)? • Memristors? • And, maybe there are other ones • Can they be enabled to replace/augment/surpass DRAM?

  6. Agenda • Major Trends Affecting Main Memory • Requirements from an Ideal Main Memory System • Opportunity: Emerging Memory Technologies • Background • PCM (or Technology X) as DRAM Replacement • Hybrid Memory Systems • Conclusions • Discussion

  7. Charge vs. Resistive Memories • Charge Memory (e.g., DRAM, Flash) • Write data by capturing charge Q • Read data by detecting voltage V • Resistive Memory (e.g., PCM, STT-MRAM, memristors) • Write data by pulsing current dQ/dt • Read data by detecting resistance R

  8. Limits of Charge Memory • Difficult charge placement and control • Flash: floating gate charge • DRAM: capacitor charge, transistor leakage • Reliable sensing becomes difficult as charge storage unit size reduces

  9. Emerging Resistive Memory Technologies • PCM • Inject current to change material phase • Resistance determined by phase • STT-MRAM • Inject current to change magnet polarity • Resistance determined by polarity • Memristors • Inject current to change atomic structure • Resistance determined by atom distance

  10. What is Phase Change Memory? • Phase change material (chalcogenide glass) exists in two states: • Amorphous: Low optical reflexivity and high electrical resistivity • Crystalline: High optical reflexivity and low electrical resistivity PCM is resistive memory: High resistance (0), Low resistance (1) PCM cell can be switched between states reliably and quickly

  11. Large Current Small Current Memory Element RESET (amorph) High resistance SET (cryst) Low resistance Access Device 106-107 W 103-104 W How Does PCM Work? • Write: change phase via current injection • SET: sustained current to heat cell above Tcryst • RESET: cell heated above Tmelt and quenched • Read: detect phase via material resistance • amorphous/crystalline Photo Courtesy: Bipin Rajendran, IBM Slide Courtesy: Moinuddin Qureshi, IBM

  12. Opportunity: PCM Advantages • Scales better than DRAM, Flash • Requires current pulses, which scale linearly with feature size • Expected to scale to 9nm (2022 [ITRS]) • Prototyped at 20nm (Raoux+, IBM JRD 2008) • Can be denser than DRAM • Can store multiple bits per cell due to large resistance range • Prototypes with 2 bits/cell in ISSCC’08, 4 bits/cell by 2012 • Non-volatile • Retain data for >10 years at 85C • No refresh needed, low idle power

  13. Phase Change Memory Properties • Surveyed prototypes from 2003-2008 (ITRS, IEDM, VLSI, ISSCC) • Derived PCM parameters for F=90nm • Lee, Ipek, Mutlu, Burger, “Architecting Phase Change Memory as a Scalable DRAM Alternative,” ISCA 2009.

  14. Phase Change Memory Properties: Latency • Latency comparable to, but slower than DRAM • Read Latency • 50ns: 4x DRAM, 10-3x NAND Flash • Write Latency • 150ns: 12x DRAM • Write Bandwidth • 5-10 MB/s: 0.1x DRAM, 1x NAND Flash

  15. Phase Change Memory Properties • Dynamic Energy • 40 uA Rd, 150 uA Wr • 2-43x DRAM, 1x NAND Flash • Endurance • Writes induce phase change at 650C • Contacts degrade from thermal expansion/contraction • 108 writes per cell • 10-8x DRAM, 103x NAND Flash • Cell Size • 9-12F2 using BJT, single-level cells • 1.5x DRAM, 2-3x NAND (will scale with feature size, MLC)

  16. Phase Change Memory: Pros and Cons • Pros over DRAM • Better technology scaling • Non volatility • Low idle power (no refresh) • Cons • Higher latencies: ~4-15x DRAM (especially write) • Higher active energy: ~2-50x DRAM (especially write) • Lower endurance (a cell dies after ~108 writes) • Challenges in enabling PCM as DRAM replacement/helper: • Mitigate PCM shortcomings • Find the right way to place PCM in the system • Ensure secure and fault-tolerant PCM operation

  17. PCM-based Main Memory: Research Challenges • Where to place PCM in the memory hierarchy? • Hybrid OS controlled PCM-DRAM • Hybrid OS controlled PCM and hardware-controlled DRAM • Pure PCM main memory • How to mitigate shortcomings of PCM? • How to minimize amount of DRAM in the system? • How to take advantage of (byte-addressable and fast) non-volatile main memory? • Can we design specific-NVM-technology-agnostic techniques?

  18. PCM-based Main Memory (I) • How should PCM-based (main) memory be organized? • Hybrid PCM+DRAM [Qureshi+ ISCA’09, Dhiman+ DAC’09, Meza+ IEEE CAL’12]: • How to partition/migrate data between PCM and DRAM

  19. Hybrid Memory Systems: Challenges • Partitioning • Should DRAM be a cache or main memory, or configurable? • What fraction? How many controllers? • Data allocation/movement (energy, performance, lifetime) • Who manages allocation/movement? • What are good control algorithms? • How do we prevent degradation of service due to wearout? • Design of cache hierarchy, memory controllers, OS • Mitigate PCM shortcomings, exploit PCM advantages • Design of PCM/DRAM chips and modules • Rethink the design of PCM/DRAM with new requirements

  20. PCM-based Main Memory (II) • How should PCM-based (main) memory be organized? • Pure PCM main memory [Lee et al., ISCA’09, Top Picks’10]: • How to redesign entire hierarchy (and cores) to overcome PCM shortcomings

  21. Aside: STT-RAM Basics • Magnetic Tunnel Junction (MTJ) • Reference layer: Fixed • Free layer: Parallel or anti-parallel • Cell • Access transistor, bit/sense lines • Read and Write • Read: Apply a small voltage across bitline and senseline; read the current. • Write: Push large current through MTJ. Direction of current determines new orientation of the free layer. • Kultursay et al., “Evaluating STT-RAM as an Energy-Efficient Main Memory Alternative,” ISPASS 2013 Word Line MTJ Access Transistor Logical 0 Sense Line Bit Line Reference Layer Barrier Free Layer Logical 1 Reference Layer Barrier Free Layer

  22. Aside: STT MRAM: Pros and Cons • Pros over DRAM • Better technology scaling • Non volatility • Low idle power (no refresh) • Cons • Higher write latency • Higher write energy • Reliability? • Another level of freedom • Can trade off non-volatility for lower write latency/energy (by reducing the size of the MTJ)

  23. Agenda • Major Trends Affecting Main Memory • Requirements from an Ideal Main Memory System • Opportunity: Emerging Memory Technologies • Background • PCM (or Technology X) as DRAM Replacement • Hybrid Memory Systems • Conclusions • Discussion

  24. An Initial Study: Replace DRAM with PCM • Lee, Ipek, Mutlu, Burger, “Architecting Phase Change Memory as a Scalable DRAM Alternative,” ISCA 2009. • Surveyed prototypes from 2003-2008 (e.g. IEDM, VLSI, ISSCC) • Derived “average” PCM parameters for F=90nm

  25. Results: Naïve Replacement of DRAM with PCM • Replace DRAM with PCM in a 4-core, 4MB L2 system • PCM organized the same as DRAM: row buffers, banks, peripherals • 1.6x delay, 2.2x energy, 500-hour average lifetime • Lee, Ipek, Mutlu, Burger, “Architecting Phase Change Memory as a Scalable DRAM Alternative,” ISCA 2009.

  26. Architecting PCM to Mitigate Shortcomings • Idea 1: Use multiple narrow row buffers in each PCM chip  Reduces array reads/writes  better endurance, latency, energy • Idea 2: Write into array at cache block or word granularity  Reduces unnecessary wear PCM DRAM

  27. Results: Architected PCM as Main Memory • 1.2x delay, 1.0x energy, 5.6-year average lifetime • Scaling improves energy, endurance, density • Caveat 1: Worst-case lifetime is much shorter (no guarantees) • Caveat 2: Intensive applications see large performance and energy hits • Caveat 3: Optimistic PCM parameters?

  28. Agenda • Major Trends Affecting Main Memory • Requirements from an Ideal Main Memory System • Opportunity: Emerging Memory Technologies • Background • PCM (or Technology X) as DRAM Replacement • Hybrid Memory Systems • Conclusions • Discussion

  29. Hybrid Memory Systems Meza, Chang, Yoon, Mutlu, Ranganathan, “Enabling Efficient and Scalable Hybrid Memories,” IEEE Comp. Arch. Letters, 2012. CPU PCM Ctrl DRAMCtrl DRAM Phase Change Memory (or Tech. X) Fast, durable Small, leaky, volatile, high-cost Large, non-volatile, low-cost Slow, wears out, high active energy Hardware/software manage data allocation and movement to achieve the best of multiple technologies

  30. One Option: DRAM as a Cache for PCM • PCM is main memory; DRAM caches memory rows/blocks • Benefits: Reduced latency on DRAM cache hit; write filtering • Memory controller hardware manages the DRAM cache • Benefit: Eliminates system software overhead • Three issues: • What data should be placed in DRAM versus kept in PCM? • What is the granularity of data movement? • How to design a low-cost hardware-managed DRAM cache? • Two idea directions: • Locality-aware data placement [Yoon+ , ICCD 2012] • Cheap tag stores and dynamic granularity [Meza+, IEEE CAL 2012]

  31. Row Buffer Locality AwareCaching Policies for Hybrid Memories HanBin Yoon Justin Meza RachataAusavarungnirunRachael Harding OnurMutlu

  32. Hybrid Memory: A Closer Look CPU Memory channel Row buffer MC MC Bank Bank Bank Bank DRAM (small capacity cache) PCM(large capacity store)

  33. Key Observation • Row buffers exist in both DRAM and PCM • Row hit latency similarin DRAM & PCM [Lee+ ISCA’09] • Row miss latency small in DRAM, large in PCM • Place data in DRAM which • is likely tomiss in the row buffer (low row buffer locality) miss penalty is smaller in DRAM AND • is reusedmany times  cache only the data worth the movement cost and DRAM space

  34. RBL-Awareness: An Example Let’s say a processor accesses four rows Row A Row B Row C Row D

  35. RBL-Awareness: An Example Let’s say a processor accesses four rowswith different row buffer localities (RBL) Row A Row B Row C Row D Low RBL (Frequently miss in row buffer) High RBL (Frequently hit in row buffer) Case 1: RBL-Unaware Policy (state-of-the-art) Case 2: RBL-Aware Policy (RBLA)

  36. Case 1: RBL-Unaware Policy A row buffer locality-unaware policy could place these rows in the following manner Row C Row A Row D Row B DRAM(High RBL) PCM(Low RBL)

  37. Case 1: RBL-Unaware Policy Access pattern to main memory: A (oldest), B, C, C, C, A, B, D, D, D, A, B (youngest) time DRAM (High RBL) C C C D D D PCM(Low RBL) A B A B A B RBL-Unaware: Stall time is 6 PCM device accesses

  38. Case 2: RBL-Aware Policy (RBLA) A row buffer locality-awarepolicy wouldplace these rows in the oppositemanner Row A Row C Row B Row D DRAM(Low RBL) PCM(High RBL)  Access data at lower row buffer miss latency of DRAM  Access data at low row buffer hit latency of PCM

  39. Case 2: RBL-Aware Policy (RBLA) Access pattern to main memory: A (oldest), B, C, C, C, A, B, D, D, D, A, B (youngest) time DRAM (High RBL) C C C D D D PCM(Low RBL) A B A B A B RBL-Unaware: Stall time is 6 PCM device accesses DRAM (Low RBL) B A B A A B PCM(High RBL) C C C D D D Saved cycles RBL-Aware: Stall time is 6 DRAM device accesses

  40. Our Mechanism: RBLA • For recently used rows in PCM: • Count row buffer misses as indicator of row buffer locality (RBL) • Cache to DRAM rows with misses threshold • Row buffer miss counts are periodically reset (only cache rows with high reuse)

  41. Our Mechanism: RBLA-Dyn • For recently used rows in PCM: • Count row buffer misses as indicator of row buffer locality (RBL) • Cache to DRAM rows with missesthreshold • Row buffer miss counts are periodically reset (only cache rows with high reuse) • Dynamically adjust threshold to adapt to workload/system characteristics • Interval-based cost-benefit analysis

  42. Implementation: “Statistics Store” • Goal: To keep count of row buffer misses to recently used rows in PCM • Hardware structure in memory controller • Operation is similar to a cache • Input: row address • Output: row buffer miss count • 128-set 16-way statistics store (9.25KB) achieves system performance within 0.3% of an unlimited-sized statistics store

  43. Evaluation Methodology • Cycle-level x86 CPU-memory simulator • CPU: 16 out-of-order cores, 32KB private L1 per core, 512KB shared L2 per core • Memory: 1GB DRAM (8 banks), 16GB PCM (8 banks), 4KB migration granularity • 36 multi-programmed server, cloud workloads • Server: TPC-C (OLTP), TPC-H (Decision Support) • Cloud: Apache (Webserv.), H.264 (Video), TPC-C/H • Metrics: Weighted speedup (perf.), perf./Watt (energy eff.), Maximum slowdown (fairness)

  44. Comparison Points • Conventional LRU Caching • FREQ: Access-frequency-based caching • Places “hot data” in cache[Jiang+ HPCA’10] • Cache to DRAM rows with accesses threshold • Row buffer locality-unaware • FREQ-Dyn: Adaptive Freq.-based caching • FREQ + our dynamic threshold adjustment • Row buffer locality-unaware • RBLA: Row buffer locality-aware caching • RBLA-Dyn: Adaptive RBL-aware caching

  45. System Performance 10% 14% 17% Benefit 1: Increased row buffer locality (RBL) in PCM by moving low RBL data to DRAM Benefit 1: Increased row buffer locality (RBL) in PCM by moving low RBL data to DRAM Benefit 2: Reduced memory bandwidth consumption due to stricter caching criteria Benefit 2: Reduced memory bandwidth consumption due to stricter caching criteria Benefit 3: Balanced memory request load between DRAM and PCM

  46. Average Memory Latency 14% 12% 9%

  47. Memory Energy Efficiency 13% 10% 7% Increased performance & reduced data movement between DRAM and PCM

  48. Thread Fairness 7.6% 6.2% 4.8%

  49. Compared to All-PCM/DRAM 29% 31% Our mechanism achieves 31% better performance than all PCM, within 29% of all DRAM performance

More Related